Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    em dashes and hyphens used for emphasis or separation in text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    icable
    -0.67
     commun
    -0.66
    ...]
    -0.63
    orts
    -0.63
    aimon
    -0.62
    ruck
    -0.60
    enei
    -0.59
    iard
    -0.59
    iple
    -0.59
    pei
    -0.59
    POSITIVE LOGITS
    ————
    1.29
    ————————
    1.28
    perhaps
    1.12
    _-
    1.10
    especially
    1.10
    particularly
    1.09
    albeit
    1.09
     namely
    1.05
    including
    1.01
    something
    0.95
    Act Density 0.452%

    No Known Activations